Machine Learning System for Targeted Event Communication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication systems waste power and processing resources by transmitting unsolicited communications to users, and by sending communications that are not relevant due to high event levels or user location.
Innovation Solution
A system that uses machine learning to predict event levels and user locations, allowing it to selectively target communications only to users who are likely to respond and are relevant to the event, thereby conserving resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If communications are transmitted to all users, then communication coverage is improved, but power consumption and processing resources increase
Solution Approach 1:
The system performs preliminary actions by predicting event levels and user locations before transmitting communications. The machine learning model forecasts event attendance levels and user positions in advance, allowing the system to pre-determine which communications should be sent, thereby avoiding wasted power on unlikely-to-engage users
Solution Approach 2:
The system incorporates feedback mechanisms where user engagement responses are fed back into the machine learning model to continuously improve prediction accuracy. This feedback loop refines the identification of users likely to engage, progressively optimizing power consumption while maintaining communication coverage
2Reliability
If communications are transmitted to all users, then communication coverage is improved, but processing resources and network overhead increase
Solution Approach 1:
The system performs preliminary filtering by predicting event levels and user locations before communication transmission. The machine learning model pre-identifies the subset of users likely to engage, allowing the system to prepare and transmit only relevant communications, thereby reducing processing resources and network overhead while maintaining effective communication coverage
Solution Approach 2:
The system extracts and isolates the relevant subset of users from the entire user base by using machine learning predictions. By taking out only those users predicted to engage with the communication based on event level and location criteria, the system reduces the processing burden and network overhead associated with transmitting to all users
3Reliability
If communications are sent based on high event levels, then user engagement is improved, but resource waste increases due to irrelevant communications
Solution Approach 1:
The system applies local quality by differentiating treatment for different user groups based on their predicted engagement likelihood. Instead of uniform communication transmission, the machine learning model identifies specific local conditions (user location relative to event, predicted engagement probability) and tailors communication sending decisions accordingly, thereby improving engagement while reducing resource waste on irrelevant communications
Solution Approach 2:
The system changes parameters by using machine learning to dynamically adjust communication sending decisions based on predicted event levels and user locations. By varying the threshold parameters for when to send communications based on real-time predictions, the system optimizes user engagement while minimizing energy loss from sending communications to users unlikely to engage
Data Source
AI summary
In some implementations, a machine learning system may generate a predicted event level, associated with an entity, based on event information associated with the entity. The machine learning system may determine that the predicted event level satisfies a threshold. The machine learning system may select, in response to determining that the predicted event level satisfies the threshold, a set of users. The machine learning system may transmit at least one communication to one or more user devices associated with the set of users.